ydixon / yolo_v3 Goto Github PK
View Code? Open in Web Editor NEWYoloV3 in Pytorch and Jupyter Notebook
YoloV3 in Pytorch and Jupyter Notebook
Hi ydixon,
I'm trying to run train custom data. In this notebook , some functions are imported from transformers.py and they are using somewhere else. But these functions are not exists in transformers.py.
For example : BoundingBoxFormatConvert,ToX1y1x2y2Abs
I think you moved these functions. Can you update repo ?
Thank you ..
from transforms import BoundingBoxFormatConvert,ToX1y1x2y2Abs, ToCxcywhRel, ToIaa, iaa_hsv_aug, iaa_random_crop, iaa_letterbox, \
IaaAugmentations, ToNp, IaaLetterbox, ToTensor, Compose
some classes and functions in "transforms.py" module (such as "BoundingBoxFormatConvert","ToX1y1x2y2Abs", "ToCxcywhRel", "ToIaa", "ToNP") seems not to be defined.
AttributeError Traceback (most recent call last)
in
18 model_id=model_id, weight_dir=weight_dir,
19 checkpoint=None, checkpoint_interval=checkpoint_interval,
---> 20 use_gpu=True)
C:\AI\yolo_v3\train.py in train(data, net, optimizer, recorder, model_id, weight_dir, checkpoint, checkpoint_interval, use_gpu)
30 train_impl(data, net, optimizer, recorder, None,
31 model_id, weight_dir, checkpoint_interval,
---> 32 use_gpu)
33
34 def train_impl(data, net, optimizer, recorder, scheduler,
C:\AI\yolo_v3\train.py in train_impl(data, net, optimizer, recorder, scheduler, model_id, weight_dir, checkpoint_interval, use_gpu, debug_log)
43
44 # data will generate mini-batches of sample
---> 45 for sample in data:
46 # batch - mini-batch index, net_batch - net batch index, epoch - epoch index
47 batch, net_batch, epoch = data.get_batch(), data.get_net_batch(), data.get_epoch()
C:\AI\yolo_v3\dataset.py in gen(self)
352 def gen(self):
353 while self.current_batch < self.max_batches:
--> 354 for i in self.dataloader:
355 yield(i)
356 self.current_batch += 1
~\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py in iter(self)
277 return _SingleProcessDataLoaderIter(self)
278 else:
--> 279 return _MultiProcessingDataLoaderIter(self)
280
281 @Property
~\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py in init(self, loader)
717 # before it starts, and del tries to join but will get:
718 # AssertionError: can only join a started process.
--> 719 w.start()
720 self._index_queues.append(index_queue)
721 self._workers.append(w)
~\Anaconda3\lib\multiprocessing\process.py in start(self)
110 'daemonic processes are not allowed to have children'
111 _cleanup()
--> 112 self._popen = self._Popen(self)
113 self._sentinel = self._popen.sentinel
114 # Avoid a refcycle if the target function holds an indirect
~\Anaconda3\lib\multiprocessing\context.py in _Popen(process_obj)
221 @staticmethod
222 def _Popen(process_obj):
--> 223 return _default_context.get_context().Process._Popen(process_obj)
224
225 class DefaultContext(BaseContext):
~\Anaconda3\lib\multiprocessing\context.py in _Popen(process_obj)
320 def _Popen(process_obj):
321 from .popen_spawn_win32 import Popen
--> 322 return Popen(process_obj)
323
324 class SpawnContext(BaseContext):
~\Anaconda3\lib\multiprocessing\popen_spawn_win32.py in init(self, process_obj)
87 try:
88 reduction.dump(prep_data, to_child)
---> 89 reduction.dump(process_obj, to_child)
90 finally:
91 set_spawning_popen(None)
~\Anaconda3\lib\multiprocessing\reduction.py in dump(obj, file, protocol)
58 def dump(obj, file, protocol=None):
59 '''Replacement for pickle.dump() using ForkingPickler.'''
---> 60 ForkingPickler(file, protocol).dump(obj)
61
62 #
AttributeError: Can't pickle local object 'get_trans_fn..getTransformByDim'
import imgaug as ia
from imgaug import augmenters as iaa
where is imgaug?
It sounds like the code does not work with yolo_tiny from pjreddie
COCO_ydixon weights 是已经训练好的权重文件吗
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.